Dustin Scheinost
@dscheinost.bsky.social
Associate Prof in Yale Radiology & Biomedical Imaging (he/him/his) functional connectivity | predictive modeling | fetal-infant fMRI co-founder @fitngin.bsky.social | developer https://bioimagesuiteweb.github.io/alphaapp/ medicine.yale.edu/lab/scheinost
A Perspective discusses the use of external validation using independent datasets for improving human neuroimaging studies. @dscheinost.bsky.social @matt-rosenblatt.bsky.social www.nature.com/articles/s41...
External validation improves generalizability, replicability and reproducibility in predictive models for neuroimaging - Nature Methods
This Perspective promotes the use of external validation using independent datasets for human neuroimaging studies.
nature.com
External validation is a great way to improve rigor in neuroimaging. Although a simple idea is simple—test a predictive model on another dataset—the practice is not. In our Perspective in @natmethods.nature.com, we discuss practical issues and solutions; www.nature.com/articles/s41...
External validation improves generalizability, replicability and reproducibility in predictive models for neuroimaging - Nature Methods
This Perspective promotes the use of external validation using independent datasets for human neuroimaging studies.
nature.com
External validation is a great way to improve rigor in neuroimaging. Although a simple idea is simple—test a predictive model on another dataset—the practice is not. In our Perspective in @natmethods.nature.com, we discuss practical issues and solutions; www.nature.com/articles/s41...
External validation improves generalizability, replicability and reproducibility in predictive models for neuroimaging - Nature Methods
This Perspective promotes the use of external validation using independent datasets for human neuroimaging studies.
nature.com
Feature selection leads to divergent neurobiological interpretations of brain-based machine learning biomarkers
Feature selection leads to divergent neurobiological interpretations of brain-based machine learning biomarkers
Nature Human Behaviour, Published online: 15 April 2026; doi:10.1038/s41562-026-02447-yAcross more than 12,000 MRI scans, the authors show that features discarded during feature selection can rival top-ranked ones in predicting behaviour yet imply different brain circuits, warning that focusing only on top features can mislead neurobiology.
dlvr.it
⌛ Abstract and symposium submissions are due in just ONE week!!! 📅 Deadline: 25 February Don’t miss your chance to share your work 🔬 🧠 🔗 Abstracts: fitng.org/poster-oral-... 🔗 Symposium: fitng.org/symposium-su... #FITNG2026 #OHBM2026 #ISMRM2026
a black cat is using an apple laptop with the words deadline is coming written below it
ALT: a black cat is using an apple laptop with the words deadline is coming written below it
media.tenor.com
⏰ Deadline Alert!!! Abstract & Symposium submissions close on 25 February. Wrap up your analyses and submit now 👇 🌐 Abstracts: fitng.org/poster-oral-... 🌐 Symposium: fitng.org/symposium-su... #FITNG2026
In a recent @cp-neuron.bsky.social study, @dscheinost.bsky.social and @yaleschoolofmed.bsky.social's Jean Ye found that neural variability 🧠—brain fluctuations that support flexible behavior—increases 📈 through childhood 👶before stabilizing in adolescence🧍
Brain Activity is Increasingly Variable During Development
Fluctuations in brain activity increase until mid-adolescence. Deviations from this trajectory are linked to worse executive functioning.
medicine.yale.edu
Excited to share our work now out in @cp-neuron.bsky.social !!! We found that during development, people become more variable in how much they engage recurring brain states.
Very excited for this review to be out! A dive into PET/MRS techniques for measuring brain glucose concentrations and cerebral metabolic rate of glucose in the context of diabetes and obesity. #neuroimaging #obesity #diabetes #metabolism #neuroendocrinology link.springer.com/article/10.1...
It is more important than ever to promote inclusive & representative science as best scientific practice. In this new paper, we highlight modality-level (MRI, MEG, EEG, fNIRS, ultrasound) obstacles & initiatives for improved inclusivity in FIT neuroimaging. doi.org/10.1016/j.dcn.2024.101505
📢 In a new study, @yaleschoolofmed.bsky.social's Jean Ye, @evgoldfarb.bsky.social, & @dscheinost.bsky.social found that people with opioid use disorder had less cognitive flexibility in engaging different brain states 🧠after viewing opioid-related images💊📷 Read More 👇
Opioid use disorder might lead to ‘sticky’ brains
Individuals with opioid use disorder were less able to flexibly engage different patterns of brain activity, Yale researchers found.
news.yale.edu
Happy New Year! The first working day of 2025 is off to a FANTASTIC start, with news that our paper with the FITNG Trainee Committee @fitngin.bsky.social has been accepted for publication in DCN! Wahooooooo 🥳 www.sciencedirect.com/science/arti...
Modality-Level Obstacles and Initiatives to Improve Representation in Fetal, Infant, and Toddler Neuroimaging Research Samples
Fetal, infant, and toddler (FIT) neuroimaging researchers study early brain development to gain insights into neurodevelopmental processes and identif…
sciencedirect.com
Thrilled to share Jean Ye’s latest paper on brain dynamics in opioid use disorder (OUD), using resting-state, task-based, and naturalistic fMRI! Check it out at Jama Network Open: jamanetwork.com/journals/jam...
Neural Variability and Cognitive Control in Individuals With Opioid Use Disorder
This case-control study compares functional magnetic resonance imaging data from individuals with opioid use disorder (OUD) and healthy control participants to examine whether individuals with OUD hav...
jamanetwork.com
Thrilled to share Jean Ye’s latest paper on brain dynamics in opioid use disorder (OUD), using resting-state, task-based, and naturalistic fMRI! Check it out at Jama Network Open: jamanetwork.com/journals/jam...
Neural Variability and Cognitive Control in Individuals With Opioid Use Disorder
This case-control study compares functional magnetic resonance imaging data from individuals with opioid use disorder (OUD) and healthy control participants to examine whether individuals with OUD hav...
jamanetwork.com